Status DBImpl::Write(const WriteOptions& options, WriteBatch* updates) {
  Writer w(&mutex_);
  w.batch = updates;
  w.sync = options.sync;
  w.done = false;

  MutexLock l(&mutex_);
  writers_.push_back(&w);
  while (!w.done && &w != writers_.front()) {
    w.cv.Wait();
  }
  if (w.done) {
    return w.status;
  }

  // May temporarily unlock and wait.
  Status status = MakeRoomForWrite(updates == nullptr);
  uint64_t last_sequence = versions_->LastSequence();
  Writer* last_writer = &w;
  if (status.ok() && updates != nullptr) {  // nullptr batch is for compactions
    WriteBatch* write_batch = BuildBatchGroup(&last_writer);
    WriteBatchInternal::SetSequence(write_batch, last_sequence + 1);
    last_sequence += WriteBatchInternal::Count(write_batch);

    // Add to log and apply to memtable.  We can release the lock
    // during this phase since &w is currently responsible for logging
    // and protects against concurrent loggers and concurrent writes
    // into mem_.
    {
      mutex_.Unlock();
      status = log_->AddRecord(WriteBatchInternal::Contents(write_batch));
      bool sync_error = false;
      if (status.ok() && options.sync) {
        status = logfile_->Sync();
        if (!status.ok()) {
          sync_error = true;
        }
      }
      if (status.ok()) {
        status = WriteBatchInternal::InsertInto(write_batch, mem_);
      }
      mutex_.Lock();
      if (sync_error) {
        // The state of the log file is indeterminate: the log record we
        // just added may or may not show up when the DB is re-opened.
        // So we force the DB into a mode where all future writes fail.
        RecordBackgroundError(status);
      }
    }
    if (write_batch == tmp_batch_) tmp_batch_->Clear();

    versions_->SetLastSequence(last_sequence);
  }

  while (true) {
    Writer* ready = writers_.front();
    writers_.pop_front();
    if (ready != &w) {
      ready->status = status;
      ready->done = true;
      ready->cv.Signal();
    }
    if (ready == last_writer) break;
  }

  // Notify new head of write queue
  if (!writers_.empty()) {
    writers_.front()->cv.Signal();
  }

  return status;
}

Status Writer::AddRecord(const Slice& slice) {
  const char* ptr = slice.data();
  size_t left = slice.size();

  // Fragment the record if necessary and emit it.  Note that if slice
  // is empty, we still want to iterate once to emit a single
  // zero-length record
  Status s;
  bool begin = true;
  do {
    const int leftover = kBlockSize - block_offset_;
    assert(leftover >= 0);
    if (leftover < kHeaderSize) {
      // Switch to a new block
      if (leftover > 0) {
        // Fill the trailer (literal below relies on kHeaderSize being 7)
        static_assert(kHeaderSize == 7, "");
        dest_->Append(Slice("\x00\x00\x00\x00\x00\x00", leftover));
      }
      block_offset_ = 0;
    }

    // Invariant: we never leave < kHeaderSize bytes in a block.
    assert(kBlockSize - block_offset_ - kHeaderSize >= 0);

    const size_t avail = kBlockSize - block_offset_ - kHeaderSize;
    const size_t fragment_length = (left < avail) ? left : avail;

    RecordType type;
    const bool end = (left == fragment_length);
    if (begin && end) {
      type = kFullType;
    } else if (begin) {
      type = kFirstType;
    } else if (end) {
      type = kLastType;
    } else {
      type = kMiddleType;
    }

    s = EmitPhysicalRecord(type, ptr, fragment_length);
    ptr += fragment_length;
    left -= fragment_length;
    begin = false;
  } while (s.ok() && left > 0);
  return s;
}

Status Writer::EmitPhysicalRecord(RecordType t, const char* ptr,
                                  size_t length) {
  assert(length <= 0xffff);  // Must fit in two bytes
  assert(block_offset_ + kHeaderSize + length <= kBlockSize);

  // Format the header
  char buf[kHeaderSize];
  buf[4] = static_cast<char>(length & 0xff);
  buf[5] = static_cast<char>(length >> 8);
  buf[6] = static_cast<char>(t);

  // Compute the crc of the record type and the payload.
  uint32_t crc = crc32c::Extend(type_crc_[t], ptr, length);
  crc = crc32c::Mask(crc);  // Adjust for storage
  EncodeFixed32(buf, crc);

  // Write the header and the payload
  Status s = dest_->Append(Slice(buf, kHeaderSize));
  if (s.ok()) {
    s = dest_->Append(Slice(ptr, length));
    if (s.ok()) {
      s = dest_->Flush();
    }
  }
  block_offset_ += kHeaderSize + length;
  return s;
}

Status WriteBatchInternal::InsertInto(const WriteBatch* b, MemTable* memtable) {
  MemTableInserter inserter;
  inserter.sequence_ = WriteBatchInternal::Sequence(b);
  inserter.mem_ = memtable;
  return b->Iterate(&inserter);
}

Status WriteBatch::Iterate(Handler* handler) const {
  Slice input(rep_);
  if (input.size() < kHeader) {
    return Status::Corruption("malformed WriteBatch (too small)");
  }

  input.remove_prefix(kHeader);
  Slice key, value;
  int found = 0;
  while (!input.empty()) {
    found++;
    char tag = input[0];
    input.remove_prefix(1);
    switch (tag) {
      case kTypeValue:
        if (GetLengthPrefixedSlice(&input, &key) &&
            GetLengthPrefixedSlice(&input, &value)) {
          handler->Put(key, value);
        } else {
          return Status::Corruption("bad WriteBatch Put");
        }
        break;
      case kTypeDeletion:
        if (GetLengthPrefixedSlice(&input, &key)) {
          handler->Delete(key);
        } else {
          return Status::Corruption("bad WriteBatch Delete");
        }
        break;
      default:
        return Status::Corruption("unknown WriteBatch tag");
    }
  }
  if (found != WriteBatchInternal::Count(this)) {
    return Status::Corruption("WriteBatch has wrong count");
  } else {
    return Status::OK();
  }
}

namespace {
class MemTableInserter : public WriteBatch::Handler {
 public:
  SequenceNumber sequence_;
  MemTable* mem_;

  void Put(const Slice& key, const Slice& value) override {
    mem_->Add(sequence_, kTypeValue, key, value);
    sequence_++;
  }
  void Delete(const Slice& key) override {
    mem_->Add(sequence_, kTypeDeletion, key, Slice());
    sequence_++;
  }
};
}  // namespace

void MemTable::Add(SequenceNumber s, ValueType type, const Slice& key,
                   const Slice& value) {
  // Format of an entry is concatenation of:
  //  key_size     : varint32 of internal_key.size()
  //  key bytes    : char[internal_key.size()]
  //  value_size   : varint32 of value.size()
  //  value bytes  : char[value.size()]
  size_t key_size = key.size();
  size_t val_size = value.size();
  size_t internal_key_size = key_size + 8;
  const size_t encoded_len = VarintLength(internal_key_size) +
                             internal_key_size + VarintLength(val_size) +
                             val_size;
  char* buf = arena_.Allocate(encoded_len);
  char* p = EncodeVarint32(buf, internal_key_size);
  std::memcpy(p, key.data(), key_size);
  p += key_size;
  EncodeFixed64(p, (s << 8) | type);
  p += 8;
  p = EncodeVarint32(p, val_size);
  std::memcpy(p, value.data(), val_size);
  assert(p + val_size == buf + encoded_len);
  table_.Insert(buf);
}

Status DBImpl::Get(const ReadOptions& options, const Slice& key,
                   std::string* value) {
  Status s;
  MutexLock l(&mutex_);
  SequenceNumber snapshot;
  if (options.snapshot != nullptr) {
    snapshot =
        static_cast<const SnapshotImpl*>(options.snapshot)->sequence_number();
  } else {
    snapshot = versions_->LastSequence();
  }

  MemTable* mem = mem_;
  MemTable* imm = imm_;
  Version* current = versions_->current();
  mem->Ref();
  if (imm != nullptr) imm->Ref();
  current->Ref();

  bool have_stat_update = false;
  Version::GetStats stats;

  // Unlock while reading from files and memtables
  {
    mutex_.Unlock();
    // First look in the memtable, then in the immutable memtable (if any).
    LookupKey lkey(key, snapshot);
    if (mem->Get(lkey, value, &s)) {
      // Done
    } else if (imm != nullptr && imm->Get(lkey, value, &s)) {
      // Done
    } else {
      s = current->Get(options, lkey, value, &stats);
      have_stat_update = true;
    }
    mutex_.Lock();
  }

  if (have_stat_update && current->UpdateStats(stats)) {
    MaybeScheduleCompaction();
  }
  mem->Unref();
  if (imm != nullptr) imm->Unref();
  current->Unref();
  return s;
}